Yang yaming
|
d4a2a005ca
|
Merge pull request #2 from pkuyym/fix-1
Add ci and code format checking.
|
7 years ago |
yangyaming
|
12a1ce2570
|
Add ci and code format checking.
|
7 years ago |
Xinghai Sun
|
ecbed5565d
|
Create License
Add Apache License.
|
7 years ago |
Xinghai Sun
|
522efcaadb
|
Initial commit
|
7 years ago |
Yibing Liu
|
edaed68f33
|
Involve dev dataset to build vocabulary in the aishell example
|
7 years ago |
Yibing Liu
|
22a882e30b
|
Set the version of CTC decoders to 1.0
|
7 years ago |
Yibing Liu
|
bf69a1013b
|
Adapt tuning script to padding removing #444
|
7 years ago |
Yang yaming
|
4913cba53c
|
Merge pull request #444 from pkuyym/fix-442
Support padding removing.
|
7 years ago |
yangyaming
|
f38d948193
|
Add more comments.
|
7 years ago |
yangyaming
|
a02b8f8084
|
Add clean callback.
|
7 years ago |
yangyaming
|
b3ebf3fd62
|
Support padding removing.
|
7 years ago |
Yibing Liu
|
a0d1146be7
|
Update benchmark results for LibriSpeech model due to #427
|
7 years ago |
Yibing Liu
|
1369375b02
|
Merge pull request #427 from kuke/decoding_postprocessing
Add the scoring of last word/char of prefixes in CTC beam search decoder
|
7 years ago |
Yibing Liu
|
4b20a7029c
|
skip scoring the end when using character-based scorer
|
7 years ago |
Yibing Liu
|
fcd6149704
|
Update benchmark results for BaiduEN8K model due to #427
|
7 years ago |
Yibing Liu
|
921c6d0cc1
|
Add the scoring of last word/char of prefixes in CTC beam search decoder
|
7 years ago |
Xinghai Sun
|
1bd5cc9ff4
|
Merge pull request #422 from xinghai-sun/demo_example
Release BaiduEn8k model and prepare the corresponding demo example.
|
7 years ago |
Yibing Liu
|
f8da5127fe
|
Update benchmark results for LibriSpeech model
|
7 years ago |
Xinghai Sun
|
d58dd5fe72
|
Release BaiduEn8k model and prepare demo example.
|
7 years ago |
Xinghai Sun
|
9c897b7256
|
Merge pull request #421 from xinghai-sun/benchmark
Update DS2 benchmark results.
|
7 years ago |
Xinghai Sun
|
42ef8b3be3
|
Rename: Eng --> EN, Chi --> CN
|
7 years ago |
Xinghai Sun
|
84155d1548
|
Update DS2 benchmark results.
|
7 years ago |
Yang yaming
|
a6bffa59ec
|
Merge pull request #364 from pkuyym/fix-361
Add document for Mandarin model.
|
7 years ago |
yangyaming
|
046f6ca994
|
Refine doc.
|
7 years ago |
yangyaming
|
963b60d5ed
|
Refine doc for Mandarin training.
|
7 years ago |
Xinghai Sun
|
31d8e7e033
|
Merge pull request #418 from kuke/docker_doc_dev
Add the document about docker running for DS2
|
7 years ago |
Yibing Liu
|
6f90a33f1f
|
Update the doc about docker running for DS2
|
7 years ago |
Yibing Liu
|
3e048a3c9a
|
Add the doc about docker running for DS2
|
7 years ago |
Xinghai Sun
|
eb863f8041
|
Merge pull request #368 from pkuyym/fix-365
Add doc for Chinese LM.
|
7 years ago |
Xinghai Sun
|
3f13797a0c
|
Merge pull request #396 from pkuyym/fix-393
Give option to disable converting from transcription text to ids.
|
7 years ago |
yangyaming
|
1f6a18e8e8
|
Refine doc.
|
7 years ago |
yangyaming
|
e8a5a17b1d
|
Refine doc.
|
7 years ago |
yangyaming
|
a084394128
|
Add doc and adjust some codes.
|
7 years ago |
Yibing Liu
|
797bac454a
|
Merge pull request #383 from kuke/top_n_append_dev
Supply param cutoff_top_n in several scripts of DS2
|
7 years ago |
yangyaming
|
39dbcb4dfb
|
Give option to disable converting from transcription text to ids.
|
7 years ago |
Peng Li
|
f23282dc36
|
fix bug in saving model (invoke the wrong function)
|
7 years ago |
Yibing Liu
|
ad08dd963a
|
supply param cutoff_top_n in several scripts of DS2
|
7 years ago |
Xinghai Sun
|
81207201da
|
Fix a bug in running tools/compute_meanstd.py with seqbin data.
|
7 years ago |
yangyaming
|
d78d4fa6ff
|
Add url for large Mandarin LM.
|
7 years ago |
yangyaming
|
9b7fc7e903
|
Add doc for Chinese LM.
|
7 years ago |
Xinghai Sun
|
9ac15f8bd8
|
Merge pull request #363 from xinghai-sun/default_value
Reset default value of batch_size, num_proc_data and fix an invalid url for DS2.
|
7 years ago |
yangyaming
|
e3bb689c0e
|
Add document for Mandarin model.
|
7 years ago |
Xinghai Sun
|
86811af7a3
|
Reset default value of batch_size, nun_proc_data and fix an invalid url for DS2.
|
7 years ago |
yangyaming
|
758e9887ca
|
Bug fix for librispeech/run_train.sh.
|
7 years ago |
Xinghai Sun
|
2e5e9b8c11
|
Turn on rnn_use_batch of Paddle for accelartion.
Improve xmap_reader_mp by adding a flush thread.
|
7 years ago |
Xinghai Sun
|
8e5c2eb969
|
Update by following reviewer's comments for pull request #355.
|
7 years ago |
Xinghai Sun
|
be1fbc68a1
|
Set process daemon property and reset default value of num_proc_data arguments.
|
7 years ago |
Xinghai Sun
|
64ab19c165
|
Add multiprocess version of xmap_reader to speedup training.
Add seqbin data parser to adapt to internal 1w data training.
|
7 years ago |
Yibing Liu
|
37a29bf181
|
fix the core dump bug of DS2's training in docker
|
7 years ago |
Yibing Liu
|
3f608b3b81
|
enable the log of gradient clipping in training
|
7 years ago |